Hacker News Reader

Comment by benwikler | Hacker News Reader

Would be fascinated to see the DALL-E output for the same prompts as the ones used in this paper. If you've got DALL-E access and can try a few, please put links as replies!

View on HN

Posting a few comparisons here.

https://twitter.com/joeyliaw/status/1528856081476116480?s=21...

Imagen seems more realistic where Dall-E2 is more feel-good.

That is what I feel personally.

I agree with you, but for me, Dall·E 2 feels good because 90% of the time I can keep hitting the generate button and massage the prompt until I get something inspirational, surprisingly, or visually pleasing. Without access to Imagen, it's impossible for me to compare how much of the "realistic feels" of its images is constrained by the taste of the cherry-pickers.

Looking at these… I can’t help but wonder if these are literal examples of AI imagination?

I've started to ask myself if my own creativity is a result of random sampling from the diffusion tapestry of associated memories and experience on that topic.

What else could creativity possible be?

I do wonder what Dall-E 2 would output for a request along the lines of "A still life of a vase of flowers in a completely new art style."

Don't have access to Dall-E 2 or Imagen but I do have [1] and [2] locally and they produced [3] with that prompt.

[1] https://github.com/nerdyrodent/VQGAN-CLIP.git [2] https://github.com/CompVis/latent-diffusion.git [3] https://imgur.com/a/dCPt35K

Nice. Latent-diffusion has come out very traditional but the VQGAN/CLIP ones are fairly original.

From my experiments, the LD one doesn't seem to have been trained on as big or as tagged data set - there's a whole bunch of "in the style of X" that the VQGAN knows* about but the LD doesn't. That might have something to do with it.

See the paper here : https://gweb-research-imagen.appspot.com/paper.pdf Section E : "Comparison to GLIDE and DALL-E 2"

Imagen seems better at capturing details/nuance from the prompt, but subjectively the DALLE-2 images feel more “real” to me. Not sure why. Something about the lighting?

That feels about right. Imagen has a better text processing model, so it can tease apart the prompt, but DALLE has a rocking image part.

Reply on news.ycombinator.com